Cloud AI Model Finder: Bedrock vs Azure vs Vertex Prices

Which AI models can you run in your region, what do they cost per token, and does your data stay in-country?

This Actor searches official, daily-refreshed token prices from AWS Bedrock, Azure AI Foundry and Google Vertex AI, covering Claude, GPT, Gemini, Llama, Mistral, DeepSeek, Qwen, Grok, Kimi and hundreds more, and shows every cloud and region where a model is sold, cheapest first.

What you get

Search claude sonnet 4.5 and gpt 5 for Canada, keeping data within the geography:

Search	Model	Cloud	Region	Data processed	Input $/1M	Output $/1M
claude sonnet 4.5	Claude Sonnet 4.5	AWS	ca-central-1	regional	3.30	16.50
gpt 5	—	—	—	—	No option matches: offered in Canada only with global processing

Switch residency to Anywhere and GPT-5 appears in Azure's Canadian regions with global processing, where prompts may be handled outside Canada. That's the kind of detail that's hard to find in price lists and matters for privacy reviews.

Why use it

• Data residency built in. Every price is tagged with where your prompts are processed: in the region, within a geography (AWS geography inference, Azure Data Zone, Vertex us/eu), or globally. Filter to what your policy allows.
• Three clouds, one search. No more digging through three pricing pages that name models differently.
• The real cost of residency. In-region processing is often about 10% more than global. You see both and decide.
• Monthly estimates. Enter your monthly input and output tokens to rank options by total cost.
• Clear "no" answers. If a model isn't available under your constraints, you get an explicit row saying so, not an empty table.

Who it's for

• Architects and platform teams choosing where to deploy LLM workloads
• Privacy, security and compliance teams reviewing AI data flows (PIPEDA, Quebec Law 25, GDPR, sector rules)
• FinOps teams comparing AI spend across clouds
• AI agents answering "where can I run model X, and for how much?" (callable through the Apify MCP server)

How to use it

1. Models to find: one per line, partial names work: claude sonnet 4.5, gpt 5, gemini 2.5 flash, llama 4, deepseek. A search like gpt 5 also finds GPT-5 mini, GPT-5.4 and so on.
2. Location: Canada, United States, European Union, United Kingdom, Anywhere, or Custom regions (any region codes, e.g. ca-central-1, swedencentral).
3. Where may your prompts be processed?
   • In the region only
   • Within the geography (default)
   • Anywhere, which includes cheaper global processing
4. Optionally enter monthly tokens for a cost estimate, include batch prices, or limit to specific clouds.

Output

Field	Meaning
search	Your search term
model, provider	Model name as the cloud lists it, and its maker
cloud, region	aws / azure / gcp, and the region(s). Regions with identical prices share one row (first 6 shown, then "+N more") (GCP: us, eu, global or regional)
regions, regionCount	The full list of regions, and how many
dataProcessing	regional, geo, global or unspecified
dataProcessingDetail	Plain-language explanation for that cloud
tier	standard, or batch if requested
inputPer1M, outputPer1M, cachedInputPer1M	USD per million tokens
monthlyCostUsd	Estimate from your monthly tokens, if given
vsCheapestPct, isCheapest	How this option compares with the cheapest place to run the same model
noMatch, note	Set when nothing matches your constraints
pricesUpdatedAt	When prices were last refreshed

Pricing

$0.02 per model search that returns results. "No match" answers are free.

How each cloud describes data processing

Cloud	What the price list tells us
AWS Bedrock	Two prices per model and region: Global (cheaper; any AWS region) and in-region/in-geography. AWS charges the same for single-region and geography-limited inference, so they share one label.
Azure AI Foundry	Per region: Regional, Data Zone (US or EU) and Global deployments, where offered.
Google Vertex AI	Claude: us, eu or global. Gemini: one Regional price that applies to whichever region you deploy to, and a Global price. Google doesn't list which regions offer each model, so confirm availability in your chosen region.

Coverage and limits

• Text tokens, on-demand (plus batch if selected). Image, audio and video tokens, fine-tuning, provisioned throughput and long-context surcharges are not included yet.
• List prices in USD from each cloud's public price list. Enterprise discounts and commitments are not reflected.
• Google Vertex: only the Claude versions present in Google's public billing catalog are covered, currently the newest ones. Older Claude versions on Vertex are billed in a way the public catalog doesn't show.
• Azure model names are abbreviated in Microsoft's price list. They're cleaned up automatically, and a few may read slightly differently from the model catalog.

FAQ

Why is the same model cheaper with global processing? Clouds discount global routing because they can serve your request wherever capacity is free. In-region and in-geography processing usually cost about 10% more.

Does "regional" mean my data never leaves the country? It means the cloud processes the request in that region. Logging, abuse monitoring and support access are governed by each provider's terms, so review those for compliance decisions. This Actor tells you what is priced and offered, not what is legally sufficient.

How fresh is the data? Prices are refreshed daily from the providers' official price feeds. See pricesUpdatedAt.

Feedback

Missing a model or region you need? Open an issue on the Issues tab.